conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023
Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks ICML 2023
Trainability, Expressivity and Interpretability in Gated Neural ODEs ICML 2023
SAAL: Sharpness-Aware Active Learning ICML 2023
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference ICML 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
A Fully First-Order Method for Stochastic Bilevel Optimization ICML 2023
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability ICML 2023
Towards Deep Attention in Graph Neural Networks: Problems and Remedies ICML 2023
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023
Implicit Jacobian regularization weighted with impurity of probability output ICML 2023
On the Initialization of Graph Neural Networks ICML 2023
Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set ICML 2023
Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping ICML 2023
Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023
Global Optimization with Parametric Function Approximation ICML 2023
Understanding Plasticity in Neural Networks ICML 2023
Graph Inductive Biases in Transformers without Message Passing ICML 2023
Training Deep Surrogate Models with Large Scale Online Learning ICML 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023
Special Properties of Gradient Descent with Large Learning Rates ICML 2023
An SDE for Modeling SAM: Theory and Insights ICML 2023
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge ICML 2023
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction ICML 2023
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023